Skip to main content
main-content
Top

Tip

Swipe om te navigeren naar een ander artikel

01-04-2015 | Uitgave 4/2015

Quality of Life Research 4/2015

Multiple imputation to deal with missing EQ-5D-3L data: Should we impute individual domains or the actual index?

Tijdschrift:
Quality of Life Research > Uitgave 4/2015
Auteurs:
Claire L. Simons, Oliver Rivero-Arias, Ly-Mee Yu, Judit Simon
Belangrijke opmerkingen

Electronic supplementary material

The online version of this article (doi:10.​1007/​s11136-014-0837-y) contains supplementary material, which is available to authorized users.
Claire L. Simons and Oliver Rivero-Arias are joint lead authors.

Abstract

Purpose

Missing data are a well-known and widely documented problem in cost-effectiveness analyses alongside clinical trials using individual patient-level data. Current methodological research recommends multiple imputation (MI) to deal with missing health outcome data, but there is little guidance on whether MI for multi-attribute questionnaires, such as the EQ-5D-3L, should be carried out at domain or at summary score level. In this paper, we evaluated the impact of imputing individual domains versus imputing index values to deal with missing EQ-5D-3L data using a simulation study and developed recommendations for future practice.

Methods

We simulated missing data in a patient-level dataset with complete EQ-5D-3L data at one point in time from a large multinational clinical trial (n = 1,814). Different proportions of missing data were generated using a missing at random (MAR) mechanism and three different scenarios were studied. The performance of using each method was evaluated using root mean squared error and mean absolute error of the actual versus predicted EQ-5D-3L indices.

Results

In large sample sizes (n > 500) and a missing data pattern that follows mainly unit non-response, imputing domains or the index produced similar results. However, domain imputation became more accurate than index imputation with pattern of missingness following an item non-response. For smaller sample sizes (n < 100), index imputation was more accurate. When MI models were misspecified, both domain and index imputations were inaccurate for any proportion of missing data.

Conclusions

The decision between imputing the domains or the EQ-5D-3L index scores depends on the observed missing data pattern and the sample size available for analysis. Analysts conducting this type of exercises should also evaluate the sensitivity of the analysis to the MAR assumption and whether the imputation model is correctly specified.

Log in om toegang te krijgen

Met onderstaand(e) abonnement(en) heeft u direct toegang:

BSL Podotherapeut Totaal

Binnen de bundel kunt u gebruik maken van boeken, tijdschriften, e-learnings, web-tv's en uitlegvideo's. BSL Podotherapeut Totaal is overal toegankelijk; via uw PC, tablet of smartphone.

Extra materiaal
Supplementary material 1 (DOCX 26 kb)
11136_2014_837_MOESM1_ESM.docx
Literatuur
Over dit artikel

Andere artikelen Uitgave 4/2015

Quality of Life Research 4/2015 Naar de uitgave